Importance Sampling

Shared Foundations · Sampling · importance-sampling.yaml

Draw samples proportional to how much they contribute and divide by that density. Same expected value, far less variance, and the foundation every practical estimator in rendering is built on.

• supersedescorrects · extends
• classifiesspecializes · part-of
• substitutes forapproximates · alternative-to
• depends onrequires · validates

Colour is the family; a dashed line is the second member of it.

This node

• correctsfixes a defect in Monte Carlo Integrationuniform samples are wasted where the integrand is small

Referenced by

• specializesCosine-Weighted Hemisphere Sampling is a specific case of thiscancels the cosine factor in the integrand exactly
• requiresPath Guiding does not work without thisthe learned distribution is used as the sampling pdf
• requiresProximal Policy Optimization does not work without thisthe ratio it clips is the importance weight of reused data
• extendsResampled Importance Sampling adds capability to thisapproximates a pdf that cannot be sampled directly

References

• Background — Importance sampling on Wikipedia